CN117576225B - Indoor visible light positioning method and system based on received signal strength ratio - Google Patents
Indoor visible light positioning method and system based on received signal strength ratio Download PDFInfo
- Publication number
- CN117576225B CN117576225B CN202311599530.8A CN202311599530A CN117576225B CN 117576225 B CN117576225 B CN 117576225B CN 202311599530 A CN202311599530 A CN 202311599530A CN 117576225 B CN117576225 B CN 117576225B
- Authority
- CN
- China
- Prior art keywords
- point
- received signal
- positioning
- signal strength
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013528 artificial neural network Methods 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 28
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 238000010276 construction Methods 0.000 claims description 19
- 241000254173 Coleoptera Species 0.000 claims description 13
- 210000003608 fece Anatomy 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 241001229848 Aphodius granarius Species 0.000 claims description 6
- 230000002431 foraging effect Effects 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000009395 breeding Methods 0.000 claims description 2
- 230000001488 breeding effect Effects 0.000 claims description 2
- 239000013598 vector Substances 0.000 claims description 2
- 230000004807 localization Effects 0.000 claims 3
- 238000012360 testing method Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/16—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electromagnetism (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses an indoor visible light positioning method and system based on a received signal intensity ratio, wherein the method comprises the following steps: s1, introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of a reference point and the auxiliary positioning point, collecting the physical coordinates of the reference point and establishing a fingerprint database; s2, constructing a neural network positioning model, performing parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing the fingerprint database to obtain a visible light positioning model; s3, obtaining the received signal strength ratio of the point to be measured and the auxiliary positioning point, and obtaining the position information of the point to be measured based on the visible light positioning model. The fingerprint database established based on the received signal strength ratio is not influenced by the fluctuation of the LED transmitting power, and can still realize high-precision positioning when the LED transmitting power fluctuates.
Description
Technical Field
The invention belongs to the technical field of visible light positioning, and particularly relates to an indoor visible light positioning method and system based on a received signal intensity ratio.
Background
In recent years, with the increasing demands of society for indoor positioning, how to achieve accurate positioning indoors has become a research hotspot. Various technologies are applied to indoor positioning, such as WIFI, bluetooth, ultra Wideband (UWB), radio Frequency Identification (RFID), zigbee and the like, but the method has the defects of high cost, low positioning precision, electromagnetic interference and the like. Because the LED has the advantages of low power consumption, long service life, no pollution and the like, researchers put forward the concept of visible light communication (Visible Light Communication, VLC) based on the LED, and then put forward the visible light positioning technology. The visible light positioning technology causes extensive researches of more and more students due to the advantages of no need of complex equipment, high safety, high positioning precision and the like. Indoor visible light positioning technology based on received signal strength is widely used, but the following problems still remain: 1) Because the LED lamp is not an ideal constant light source in daily work, the transmitting power is not constant and continuously changes along with the surrounding environment, the fluctuation of the transmitting power of the LED can directly cause the fluctuation of the intensity of a receiving signal received by a receiving end, so that the stability of a positioning method based on the intensity of the receiving signal is poor, and the positioning precision is low; 2) Aiming at the situation that the room sizes are the same but the required LED transmitting power is different, the traditional positioning method based on the received signal strength value fusion neural network needs to reestablish a training fingerprint database and retrain a neural network positioning model, so that the applicability is low and the time consumption is long; 3) The neural network positioning algorithm can influence the performance of the neural network due to the initial weight and the threshold value which are randomly generated, so that the problems of low positioning speed, low positioning precision and the like are caused; 4) The group intelligent positioning algorithm has the defects of low convergence speed, easy sinking into local optimum and the like, and causes the problems of low algorithm performance, poor positioning effect and the like.
Disclosure of Invention
The invention aims to solve the defects of the prior art, and provides an indoor visible light positioning method and system based on a received signal intensity ratio, wherein the positioning accuracy can not be influenced by the fluctuation of the LED transmitting power.
In order to achieve the above object, the present invention provides the following solutions:
an indoor visible light positioning method based on a received signal strength ratio comprises the following steps:
S1, introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of a reference point and the auxiliary positioning point, collecting the physical coordinates of the reference point and establishing a fingerprint database;
S2, constructing a neural network positioning model, performing parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing the fingerprint database to obtain a visible light positioning model;
S3, obtaining the received signal strength ratio of the point to be measured and the auxiliary positioning point, and obtaining the position information of the point to be measured based on the visible light positioning model.
Preferably, the S1 includes:
Dividing the ground into n grids, and collecting the received signal strength value of the reference point and the received signal strength value of the auxiliary positioning point;
calculating the ratio of the received signal strength value of the reference point to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the reference point to the auxiliary locating point;
and collecting physical coordinates of the reference point, and constructing the fingerprint database based on the received signal strength ratio of the reference point and the auxiliary positioning point and the physical coordinates of the reference point.
Preferably, the S2 includes:
constructing the neural network positioning model based on an ELM neural network;
Optimizing the initial weight and the threshold value of the neural network positioning model by using SGDBO algorithm to obtain an optimized SGDBO-ELM neural network positioning model, namely the optimized model;
And inputting the fingerprint database into the optimized model for model training to obtain the visible light positioning model.
Preferably, the optimizing method comprises:
initializing a network structure and a dung beetle population of the neural network positioning model;
calculating the fitness value of individuals in the initial population, and the absolute value of the error between the output matrix and the reference matrix of the neural network positioning model, and taking the absolute value as an objective function of SGDBO algorithm;
calculating an optimal individual value by using an updating formula of SGDBO algorithm based on the fitness value, generating a new population, and stopping the cycle until the maximum iteration number or the target error value is reached, so as to obtain an optimal weight and an optimal threshold;
and taking the optimal weight and the optimal threshold as network parameters of the neural network positioning model to obtain the optimized model.
Preferably, the S3 includes:
Collecting the received signal strength value of the to-be-measured point and the received signal strength value of the auxiliary positioning point;
calculating the ratio of the received signal strength value of the point to be measured to the received signal strength value of the auxiliary positioning point, namely the received signal strength ratio of the point to be measured to the auxiliary positioning point;
and constructing fingerprint information of the to-be-measured point based on the received signal strength ratio of the to-be-measured point to the auxiliary positioning point, and inputting the fingerprint information into the visible light positioning model to obtain the position information of the to-be-measured point.
The invention also provides an indoor visible light positioning system based on the received signal intensity ratio, which applies the positioning method described in any one of the above, and comprises the following steps: the system comprises a database construction module, a model construction module and a positioning module;
the database construction module is used for introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of a reference point and the auxiliary positioning point, collecting the physical coordinates of the reference point and establishing a fingerprint database;
the model construction module is used for constructing a neural network positioning model, carrying out parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing the fingerprint database to obtain a visible light positioning model;
the positioning module is used for obtaining the received signal strength ratio of the point to be measured and the auxiliary positioning point, and obtaining the position information of the point to be measured based on the visible light positioning model.
Preferably, the database construction module includes: the fingerprint database comprises a first collecting unit, a first calculating unit, a constructing unit and a fingerprint database;
The first collecting unit is used for dividing the ground into n grids, and collecting the received signal strength value of the reference point and the received signal strength value of the auxiliary locating point;
The first calculating unit is used for calculating the ratio of the received signal strength value of the reference point to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the reference point to the auxiliary locating point;
The construction unit is used for collecting physical coordinates of the reference point and constructing the fingerprint database based on the received signal strength ratio of the reference point to the auxiliary locating point and the physical coordinates of the reference point.
Preferably, the model building module includes: the model generation unit is used for constructing the neural network positioning model based on the ELM neural network;
The optimizing unit is used for optimizing the initial weight and the threshold value of the neural network positioning model by using SGDBO algorithm to obtain an optimized SGDBO-ELM neural network positioning model, namely the optimized model;
The training unit is used for inputting the fingerprint database into the optimized model for model training to obtain the visible light positioning model.
Preferably, the workflow of the optimizing unit includes:
initializing a network structure and a dung beetle population of the neural network positioning model;
calculating the fitness value of individuals in the initial population, and the absolute value of the error between the output matrix and the reference matrix of the neural network positioning model, and taking the absolute value as an objective function of SGDBO algorithm;
calculating an optimal individual value by using an updating formula of SGDBO algorithm based on the fitness value, generating a new population, and stopping the cycle until the maximum iteration number or the target error value is reached, so as to obtain an optimal weight and an optimal threshold;
and taking the optimal weight and the optimal threshold as network parameters of the neural network positioning model to obtain the optimized model.
Preferably, the positioning module includes: the second collecting unit, the second calculating unit and the positioning unit;
The second collecting unit is used for collecting the received signal strength value of the to-be-measured point and the received signal strength value of the auxiliary positioning point;
the second calculating unit is used for calculating the ratio of the received signal strength value of the point to be measured to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the point to be measured to the auxiliary locating point;
The positioning unit is used for constructing fingerprint information of the to-be-measured point based on the received signal strength ratio of the to-be-measured point to the auxiliary positioning point, and inputting the fingerprint information into the visible light positioning model to obtain the position information of the to-be-measured point.
Compared with the prior art, the invention has the beneficial effects that:
(1) The fingerprint database established based on the received signal strength ratio is not influenced by the fluctuation of the LED transmitting power, and can still realize high-precision positioning when the LED transmitting power fluctuates;
(2) The neural network positioning model trained under the set scene is also suitable for other scenes with the same room size, so that the problems of re-building a training fingerprint database and repeated re-training are avoided, and the technology has stronger applicability in indoor positioning and saves time resources;
(3) According to the method, the position of the dung beetles in the propagation stage is optimized by utilizing a spiral search strategy, so that the rapid convergence of the population in a short time is avoided, the diversity of the population is reduced, and the algorithm falls into local optimum; the dynamic guiding strategy is introduced to guide generation of candidate solutions in the foraging stage of the population, so that the population can find the optimal position foraging more easily, the initial weight and the threshold of the ELM neural network are optimized by using SGDBO algorithm, the performance of the neural network is improved, the training speed of the neural network is improved, and the positioning accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the embodiments are briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of an optimization flow according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a neural network positioning model according to an embodiment of the present invention;
FIG. 4 is a schematic view of a room model according to an embodiment of the present invention;
FIG. 5 is a graph of an algorithmic error contrast distribution line in accordance with an embodiment of the present invention;
FIG. 6 is a graph of test points and predicted results based on a conventional fingerprint library under the fluctuation of LED emission power, wherein (a) is the case of fluctuation 1, and (b) is the case of fluctuation 2;
FIG. 7 is a graph showing test points and predicted results based on a fingerprint library of received signal strength ratios under fluctuation of LED emission power according to an embodiment of the present invention, wherein (a) is in case of fluctuation 1, and (b) is in case of fluctuation 2;
FIG. 8 is a schematic diagram of positioning performance under different room sizes according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Before positioning, firstly deducing that the ratio of the received signal strength of the reference point to the auxiliary positioning point is not influenced by the fluctuation of the LED emission power by a proportion method:
let the LED lamp follow lambertian radiation model when propagating in space, the receiving end (PD) channel gain at LOS link can be expressed as:
Wherein: a is the effective physical area of PD; d is the transmit-to-receiver spacing; m is a lambertian scattering coefficient; phi is the divergence angle; psi is the PD acceptance angle; phi c denotes the PD field angle; t 3 (ψ) and g (ψ) represent the optical filter gain and the optical concentrator gain in the link, respectively. When the emission power of the LED lamp is P t, the receiving power of the receiving end PD is P r:
Pr=HLOS·Pt
And establishing a fingerprint database which is not influenced by the fluctuation of the LED emission power based on the received signal intensity ratio, introducing an auxiliary positioning point with a known position into a room to be detected, and deducing the received signal intensity ratio of the reference point and the auxiliary positioning point by a proportion method so as not to be influenced by the fluctuation of the LED emission power. For the same reference point, the ratio of the received signal intensities before and after the fluctuation of the LED transmitting power is as follows:
where P T1 denotes the LED set emission power, P T2 is the LED emission power after being changed or fluctuated, P l1 is the received signal strength at the emission power of P T1, and P l2 is the received signal strength at the emission power of P T2.
For the auxiliary positioning point, the ratio of the received signal intensities before and after the LED transmitting power is changed is as follows:
Where P f1 is the received signal strength of the auxiliary anchor point at the transmit power of P T1, P f2 is the received signal strength of the auxiliary anchor point at the transmit power of P T2, and H LOS is the direct gain of the auxiliary anchor point.
From the above equation, the change of the received signal strength value received at the reference point is affected by the fluctuation of the light emitting power of the LED. When the luminous power of the LED fluctuates, the change rates of the received signal intensity values at the reference point and the auxiliary locating point can be further obtained as follows:
as can be seen from the above equation, the rate of change of the received signal value at each reference point is the same when the LED emission power is changed, irrespective of the position of the reference point itself, and affected only by the LED emission power.
When the LED emission power is changed to P T2, the ratio of the received signal strength of the reference point to the auxiliary locating point is:
It can be seen from this:
Therefore, when the LED emission power fluctuates, the ratio of the received signal strength of the reference point to the auxiliary locating point is unchanged.
Example 1
In this embodiment, as shown in fig. 1, an indoor visible light positioning method based on a received signal strength ratio includes the following steps:
S1, introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of a reference point and the auxiliary positioning point, collecting physical coordinates of the reference point and establishing a fingerprint database.
The method specifically comprises the following steps: dividing the ground into n grids, and collecting the received signal strength value of a reference point and the received signal strength value of an auxiliary positioning point; calculating the ratio of the received signal strength value of the reference point to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the reference point to the auxiliary locating point; and collecting physical coordinates of the reference point, and constructing a fingerprint database based on the received signal strength ratio of the reference point and the auxiliary locating point and the physical coordinates of the reference point.
In this embodiment, the ground is divided into n grid points, and the received signal strength values from four LEDs received by each reference point are collected, where the signal strength value of the c-th grid point is:
Rc=(Rc1,Rc2,Rc3,Rc4)
the signal strength values of the four LEDs received by the auxiliary locating point can be expressed as:
R′=(R1,R2,R3,R4)
The ratio of the signal intensity value received by each reference point to the signal intensity value received by the auxiliary locating point is calculated, and the ratio of the RSS of the PD at the c-th grid point to the RSS of the PD at the auxiliary locating point from the l-th LED lamp is as follows:
The embodiment proposes that delta cl is adopted as the characteristic of each grid point to be input into a neural network, the RSS ratio of each reference point to an auxiliary locating point and the corresponding physical coordinates are collected to establish a fingerprint database, and the fingerprint database is as follows:
s2, constructing a neural network positioning model, performing parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing a fingerprint database to obtain a visible light positioning model.
As shown in fig. 2, the method comprises: building a neural network positioning model based on the ELM neural network, wherein the model structure is shown in figure 3; optimizing the initial weight and the threshold value of the neural network positioning model by using SGDBO algorithm to obtain an optimized SGDBO-ELM neural network positioning model, namely an optimized model; and inputting the fingerprint database into the optimized model for model training to obtain the visible light positioning model.
In this embodiment, the SGDBO algorithm is designed first:
the position formula of the dung beetle population in the propagation stage is as follows:
Bi(t+1)=X*+b1×(Bi(t)-Lb*)+b2×(Bi(t)-Ub*)
Wherein, B i (t) represents the position information of the ith breeding ball in the t iteration; b 1 and b 2 are two independent random vectors; x * represents the current local optimum position of the population. Aiming at the problems that the DBO algorithm has poor global exploration capability and is easy to trap into local optimum and the like, the spiral search strategy is utilized to update the position of the dung beetles in the propagation stage, and the problems that the population is quickly converged in a short time, the diversity is reduced, the algorithm is trapped into local optimum and the like are avoided. The position formula of the dung beetle propagation stage is updated as follows:
Bi(t+1)=X*+erl.cos(2πl)×b1×(Bi(t)-Lb*)+erl.cos(2πl)×b2×(Bi(t)-Ub*)
Wherein l is an arbitrary number within the interval [ -1, 1]; r is a constant for determining the logarithmic spiral shape, a larger r can lead to too fast algorithm decay and fall into local optimum, a smaller r can lead to slow algorithm convergence speed, thus introducing an adaptive spiral search parameter r':
Wherein, beta is a self-set parameter, T is the current iteration number, and T is the maximum iteration number. Thus, the location formula based on the adaptive spiral search strategy is updated as:
Bi(t+1)=X*+erl.cos(2πl)×bl×(Bi(t)-Lb*)+erl.cos(2πl)×b2×(Bi(t)-Ub*)
in the foraging stage of the small dung beetles, the position formula is as follows:
xi(t+1)=xi(t)+C1×(xi(t)-Lbb)+C2×(xi(t)-Ubb)
Wherein x i (t) is the position of the ith small dung beetle in the t-th iteration; c 1 is a random number satisfying a normal distribution, and C 2 represents a random variable. The dynamic guiding strategy is introduced to guide the determination of the position of the foraging stage of the small dung beetles, and the position formula is updated as follows:
xi(t+1)=xi(t)+C1×(xi(t)-Lbb)+C2×(xi(t)-Ubb)+η(X*-xi(t))
wherein X * represents the current local optimal position of the population, and eta is a dynamic adjustment factor:
To avoid the impact of the randomly generated initial weights and thresholds on ELM neural network performance, the ELM neural network is optimized using SGDBO algorithm to find the optimal weights and thresholds. The optimizing method comprises the following steps: initializing a network structure and a dung beetle population of the neural network positioning model; calculating the fitness value of individuals in the initial population, and the absolute value of the error between the output matrix and the reference matrix of the neural network positioning model, and taking the absolute value as an objective function of SGDBO algorithm; based on the fitness value, calculating an optimal individual value by using an updating formula of SGDBO algorithm, and stopping the loop until the maximum iteration number or the target error value is reached, so as to obtain an optimal weight and an optimal threshold; and taking the optimal weight and the optimal threshold as network parameters of the neural network positioning model to obtain an optimized model.
Inputting a fingerprint database, dividing the fingerprint database into a training set and a testing set, carrying out normalization processing on the training set and the testing set, training an optimized model by using the training set, testing the trained model by using the testing set, and completing model training to obtain the visible light positioning model.
S3, acquiring the received signal strength ratio of the to-be-measured point and the auxiliary positioning point, and obtaining the position information of the to-be-measured point based on the visible light positioning model.
The method specifically comprises the following steps: collecting a received signal strength value of a to-be-measured point and a received signal strength value of an auxiliary positioning point; calculating the ratio of the received signal strength value of the to-be-measured point to the received signal strength value of the auxiliary positioning point, namely the received signal strength ratio of the to-be-measured point to the auxiliary positioning point; and constructing fingerprint information of the to-be-measured point based on the received signal intensity ratio of the to-be-measured point to the auxiliary positioning point, and inputting the fingerprint information into a visible light positioning model to obtain the position information of the to-be-measured point.
In this embodiment, the signal intensity values received by the PD at the point to be measured at the current time and the auxiliary positioning point are collected, and the signal intensity value of the w-th point to be measured is set as follows:
Rw=(Rw1,Rw2,Rw3,Rw4)
the signal strength values of the four LEDs received by the auxiliary locating point can be expressed as:
RE=(RE1,RE2,RE3,RE4)
the ratio of the signal intensity value of the PD at the w-th point to be detected to the PD at the auxiliary locating point from the first LED lamp is as follows:
constructing fingerprint information of the to-be-measured point based on the received signal strength ratio of the to-be-measured point:
Fw=(Δw1,Δw2,Δw3,Δw4)
Inputting the fingerprint information F w of the w-th to-be-measured point into the SGDBO-ELM neural network trained in the off-line stage to obtain an x-axis predicted coordinate x w and a y-axis predicted coordinate y w, wherein the coordinates of the w-th to-be-measured point are as follows:
W=(xw,yw)。
Example two
In this embodiment, an indoor visible light positioning system based on a received signal strength ratio includes: the system comprises a database construction module, a model construction module and a positioning module.
The database construction module is used for introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of the reference point and the auxiliary positioning point, collecting the physical coordinates of the reference point and establishing a fingerprint database.
The database construction module comprises: the fingerprint database comprises a first collecting unit, a first calculating unit, a constructing unit and a fingerprint database; the first collecting unit is used for dividing the ground into n grids, and collecting the received signal strength value of the reference point and the received signal strength value of the auxiliary locating point; the first calculation unit is used for calculating the ratio of the received signal strength value of the reference point to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the reference point to the auxiliary locating point; the construction unit is used for collecting physical coordinates of the reference point and constructing a fingerprint database based on the received signal strength ratio of the reference point and the auxiliary locating point and the physical coordinates of the reference point.
The model construction module is used for constructing a neural network positioning model, carrying out parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing the fingerprint database to obtain a visible light positioning model.
The model construction module comprises: the system comprises a model generating unit, an optimizing unit and a training unit model; the generating unit is used for constructing a neural network positioning model based on the ELM neural network; the optimizing unit is used for optimizing the initial weight and the threshold value of the neural network positioning model by using SGDBO algorithm to obtain an optimized SGDBO-ELM neural network positioning model, namely an optimized model; the training unit is used for inputting the fingerprint database into the optimized model for model training to obtain the visible light positioning model.
The workflow of the optimizing unit includes: initializing a network structure and a dung beetle population of the neural network positioning model; calculating the fitness value of individuals in the initial population, and the absolute value of the error between the output matrix and the reference matrix of the neural network positioning model, and taking the absolute value as an objective function of SGDBO algorithm; based on the fitness value, calculating an optimal individual value by using an updating formula of SGDBO algorithm to obtain an optimal weight and an optimal threshold; and taking the optimal weight and the optimal threshold as network parameters of the neural network positioning model to obtain an optimized model.
The positioning module is used for obtaining the received signal strength ratio of the to-be-measured point and the auxiliary positioning point, and obtaining the position information of the to-be-measured point based on the visible light positioning model.
The positioning module comprises: the second collecting unit, the second calculating unit and the positioning unit; the second collecting unit is used for collecting the received signal intensity value of the to-be-measured point and the received signal intensity value of the auxiliary positioning point; the second calculation unit is used for calculating the ratio of the received signal strength value of the to-be-measured point to the received signal strength value of the auxiliary positioning point, namely the received signal strength ratio of the to-be-measured point to the auxiliary positioning point; the positioning unit is used for constructing fingerprint information of the to-be-measured point based on the received signal intensity ratio of the to-be-measured point to the auxiliary positioning point, and inputting the fingerprint information into the visible light positioning model to obtain the position information of the to-be-measured point.
Example III
The present embodiment is based on the room model shown in fig. 4, the size of the positioning area is 4m×4m×3m, four LED lamps are uniformly arranged on the ceiling according to the requirement of the indoor environment, and the coordinates of the four LEDs are (-1, 3), (1, 3), (-1, 3), (1, -1, 3); dividing the ground into grids with uniform sizes as reference points, randomly selecting the position of the center of the room, which is 1.5m away from the ground, as an auxiliary positioning point, wherein the coordinates of the auxiliary positioning point are 0,0,1.5, and acquiring the received signal strength of the reference point and the auxiliary positioning point by using a PD detector.
In order to verify the improvement effect of SGDBO-ELM neural network on positioning performance, 100 groups of reference points are randomly selected from a fingerprint database to serve as test data, the rest reference points serve as training data, the prediction accuracy and positioning stability of the ELM neural network and the optimized ELM neural network are compared, 6 test results of three positioning algorithms are randomly selected, the average positioning error of each prediction result is calculated, and the positioning error is shown in figure 5.
As can be seen from FIG. 5, the six times average positioning errors of the ELM positioning model are 3.46cm, 7.41cm, 6.13cm, 4.32cm, 4.34cm and 5.32cm respectively; the average positioning errors of the DBO-ELM positioning model for 6 times are 1.79cm, 1.74cm, 1.87cm, 1.72cm, 1.65cm and 1.80cm respectively; the average positioning errors of 6 tests of SGDBO-ELM positioning model were 1.29cm, 1.37cm, 1.44cm, 1.49cm, 1.42, 1.34cm, respectively. It can be seen that the ELM positioning algorithm has low positioning accuracy, large variation amplitude and unstable positioning, while the SGDBO-ELM positioning algorithm has small positioning error and stable prediction performance.
In order to simulate fluctuation of LED emission power or different LED emission power required by different environments, the LED emission power is set to be about 8W fluctuation and is respectively set to be fluctuation 1 and fluctuation 2, RSS values received by ground grid points under different fluctuation emission powers are collected, and the influence of the change of the LED emission power on the accuracy of a traditional RSS positioning model is analyzed. When the LED transmitting power is 8W, the RSS value collected at the ground grid point trains the SGDBO-ELM neural network, and the received signal strength of the to-be-measured point collected under the conditions of fluctuation 1 and fluctuation 2 is input into the trained SGDBO-ELM for testing. The predicted point distribution is shown in fig. 6.
As can be seen from fig. 6, when the LED emission power fluctuates, most of the test points deviate from the real coordinates, the maximum positioning errors of the two conditions of fluctuation 1 and fluctuation 2 are 22.98cm and 28.92cm, the minimum positioning errors are 0.89cm and 0.52cm, and the average positioning errors are 14.29cm and 12.67cm, respectively. Therefore, under the fluctuation environment of the LED emission power, the maximum positioning error and the minimum positioning error of the SGDBO-ELM positioning prediction model based on the RSS have larger phase difference, the stability of a positioning system is low, the positioning precision is low, and the further improvement is needed.
The proposed SGDBO-ELM dynamic positioning model based on the received signal strength ratio fingerprint database is used for predicting the position coordinates of the to-be-measured point, and the positioning effect is shown in figure 7.
As can be seen from fig. 7, when the LED emission power fluctuates, the maximum positioning errors under the two power fluctuation conditions are 9.75cm and 11.65cm, the minimum positioning errors are 0.07cm and 0.08cm, and the average positioning errors are 1.41cm and 1.45cm, respectively. Therefore, when the LED emission power fluctuates, compared with the traditional positioning method, the average positioning error of the dynamic positioning method is respectively improved by 90 percent and 89 percent, and high-precision positioning is realized.
The positioning performance of ELM, DBO-ELM and SGDBO-ELM under different interatrial dimensions was compared separately. The position prediction was performed on a spatial model of a 6m×6m×3m room, and a positioning error histogram is shown in fig. 8.
As can be seen from FIG. 8, the SGDBO-ELM positioning algorithm error has a 66% duty ratio in the 0-2cm error interval, a 32% duty ratio in the 2-4 cm error interval, and the overall positioning error is stabilized within 4 cm; the error of the DBO-ELM positioning algorithm accounts for 62% in an error interval of 0-2cm, and the error of the DBO-ELM positioning algorithm accounts for 30% in an error interval of 2-4 cm; and the ELM positioning model has relatively unstable positioning error and is mainly concentrated in an error interval of 4-6 cm. When the positioning space is increased, the dynamic positioning method provided herein can still realize high-precision and stable positioning. Therefore, the SGDBO-ELM dynamic positioning method based on the received signal strength ratio has the advantages of high positioning precision, strong applicability and the like.
The above embodiments are merely illustrative of the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but various modifications and improvements made by those skilled in the art to which the present invention pertains are made without departing from the spirit of the present invention, and all modifications and improvements fall within the scope of the present invention as defined in the appended claims.
Claims (7)
1. The indoor visible light positioning method based on the received signal strength ratio is characterized by comprising the following steps of:
S1, introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of a reference point and the auxiliary positioning point, collecting the physical coordinates of the reference point and establishing a fingerprint database;
S2, constructing a neural network positioning model, performing parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing the fingerprint database to obtain a visible light positioning model;
s3, acquiring a received signal strength ratio of a point to be measured and the auxiliary positioning point, and acquiring position information of the point to be measured based on the visible light positioning model;
The step S2 comprises the following steps:
constructing the neural network positioning model based on an ELM neural network;
Optimizing the initial weight and the threshold value of the neural network positioning model by using SGDBO algorithm to obtain an optimized SGDBO-ELM neural network positioning model, namely the optimized model;
inputting the fingerprint database into the optimized model for model training to obtain the visible light positioning model;
Designing SGDBO algorithm:
the position formula of the dung beetle population in the propagation stage is as follows:
Bi(t+1)=X*+b1×(Bi(t)-Lb*)+b2×(Bi(t)-Ub*)
Wherein, B i (t) represents the position information of the ith breeding ball in the t iteration; b 1 and b 2 are two independent random vectors; x * represents the current local optimum position of the population;
aiming at the problems that the DBO algorithm has poor global exploration capability and is easy to be trapped in local optimization and the like, the position of the dung beetles in the propagation stage is updated by utilizing a spiral search strategy, and the position formula of the dung beetles in the propagation stage is updated as follows:
Bi(t+1)=X*+erl.cos(2πl)×b1×(Bi(t)-Lb*)+erl.cos(2πl)×b2×(Bi(t)-Ub*)
wherein l is an arbitrary number within the interval [ -1,1 ]; introducing an adaptive spiral search parameter r':
Wherein beta is a self-set parameter, T is the current iteration number, and T is the maximum iteration number;
the location formula based on the adaptive spiral search strategy is updated as follows:
Bi(t+1)=X*+erl.cos(2πl)×b1×(Bi(t)-Lb*)+erl.cos(2πl)×b2×(Bi(t)-Ub*)
in the foraging stage of the small dung beetles, the position formula is as follows:
xi(t+1)=xi(t)+C1×(xi(t)-Lbb)+C2×(xi(t)-Ubb)
Wherein x i (t) is the position of the ith small dung beetle in the t-th iteration; c 1 is a random number satisfying normal distribution, C 2 is a random variable;
The dynamic guiding strategy is introduced to guide the determination of the position of the foraging stage of the small dung beetles, and the position formula is updated as follows:
xi(t+1)=xi(t)+Cz×(xi(t)-Lbb)+C2×(xi(t)-Ubb)+η(X*-xi(t))
wherein X * represents the current local optimal position of the population, and eta is a dynamic adjustment factor:
the optimizing method comprises the following steps:
initializing a network structure and a dung beetle population of the neural network positioning model;
calculating the fitness value of individuals in the initial population, and the absolute value of the error between the output matrix and the reference matrix of the neural network positioning model, and taking the absolute value as an objective function of SGDBO algorithm;
calculating an optimal individual value by using an updating formula of SGDBO algorithm based on the fitness value, generating a new population, and stopping the cycle until the maximum iteration number or the target error value is reached, so as to obtain an optimal weight and an optimal threshold;
Taking the optimal weight and the optimal threshold as network parameters of the neural network positioning model to obtain the optimized model;
the step S3 comprises the following steps:
Collecting the received signal strength value of the to-be-measured point and the received signal strength value of the auxiliary positioning point;
calculating the ratio of the received signal strength value of the point to be measured to the received signal strength value of the auxiliary positioning point, namely the received signal strength ratio of the point to be measured to the auxiliary positioning point;
and constructing fingerprint information of the to-be-measured point based on the received signal strength ratio of the to-be-measured point to the auxiliary positioning point, and inputting the fingerprint information into the visible light positioning model to obtain the position information of the to-be-measured point.
2. The indoor visible light localization method based on the received signal strength ratio of claim 1, wherein S1 comprises:
Dividing the ground into n grids, and collecting the received signal strength value of the reference point and the received signal strength value of the auxiliary positioning point;
calculating the ratio of the received signal strength value of the reference point to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the reference point to the auxiliary locating point;
and collecting physical coordinates of the reference point, and constructing the fingerprint database based on the received signal strength ratio of the reference point and the auxiliary positioning point and the physical coordinates of the reference point.
3. An indoor visible light positioning system based on a received signal strength ratio, the positioning system applying the positioning method according to any one of claims 1-2, comprising: the system comprises a database construction module, a model construction module and a positioning module;
the database construction module is used for introducing an auxiliary positioning point with a known position into a room to be detected, calculating the received signal strength ratio of a reference point and the auxiliary positioning point, collecting the physical coordinates of the reference point and establishing a fingerprint database;
the model construction module is used for constructing a neural network positioning model, carrying out parameter optimization on the neural network positioning model to obtain an optimized model, and training the optimized model by utilizing the fingerprint database to obtain a visible light positioning model;
the positioning module is used for obtaining the received signal strength ratio of the point to be measured and the auxiliary positioning point, and obtaining the position information of the point to be measured based on the visible light positioning model.
4. A system for locating indoor visible light as defined in claim 3, wherein the database construction module comprises: the fingerprint database comprises a first collecting unit, a first calculating unit, a constructing unit and a fingerprint database;
The first collecting unit is used for dividing the ground into n grids, and collecting the received signal strength value of the reference point and the received signal strength value of the auxiliary locating point;
The first calculating unit is used for calculating the ratio of the received signal strength value of the reference point to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the reference point to the auxiliary locating point;
The construction unit is used for collecting physical coordinates of the reference point and constructing the fingerprint database based on the received signal strength ratio of the reference point to the auxiliary locating point and the physical coordinates of the reference point.
5. A system for indoor visible light localization based on received signal strength ratios as defined in claim 3, wherein the model building module comprises: model generation unit, optimization unit and training unit
The model generating unit is used for constructing the neural network positioning model based on the ELM neural network;
The optimizing unit is used for optimizing the initial weight and the threshold value of the neural network positioning model by using SGDBO algorithm to obtain an optimized SGDBO-ELM neural network positioning model, namely the optimized model;
The training unit is used for inputting the fingerprint database into the optimized model for model training to obtain the visible light positioning model.
6. The indoor visible light localization system based on received signal strength ratios of claim 5, wherein the workflow of the optimization unit comprises:
initializing a network structure and a dung beetle population of the neural network positioning model;
calculating the fitness value of individuals in the initial population, and the absolute value of the error between the output matrix and the reference matrix of the neural network positioning model, and taking the absolute value as an objective function of SGDBO algorithm;
calculating an optimal individual value by using an updating formula of SGDBO algorithm based on the fitness value, generating a new population, and stopping the cycle until the maximum iteration number or the target error value is reached, so as to obtain an optimal weight and an optimal threshold;
and taking the optimal weight and the optimal threshold as network parameters of the neural network positioning model to obtain the optimized model.
7. A system for locating visible light in a room based on received signal strength ratio as set forth in claim 3, wherein the locating module comprises: the second collecting unit, the second calculating unit and the positioning unit;
The second collecting unit is used for collecting the received signal strength value of the to-be-measured point and the received signal strength value of the auxiliary positioning point;
the second calculating unit is used for calculating the ratio of the received signal strength value of the point to be measured to the received signal strength value of the auxiliary locating point, namely the received signal strength ratio of the point to be measured to the auxiliary locating point;
The positioning unit is used for constructing fingerprint information of the to-be-measured point based on the received signal strength ratio of the to-be-measured point to the auxiliary positioning point, and inputting the fingerprint information into the visible light positioning model to obtain the position information of the to-be-measured point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311599530.8A CN117576225B (en) | 2023-11-28 | 2023-11-28 | Indoor visible light positioning method and system based on received signal strength ratio |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311599530.8A CN117576225B (en) | 2023-11-28 | 2023-11-28 | Indoor visible light positioning method and system based on received signal strength ratio |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117576225A CN117576225A (en) | 2024-02-20 |
CN117576225B true CN117576225B (en) | 2024-05-31 |
Family
ID=89891488
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311599530.8A Active CN117576225B (en) | 2023-11-28 | 2023-11-28 | Indoor visible light positioning method and system based on received signal strength ratio |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117576225B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105823477A (en) * | 2016-03-09 | 2016-08-03 | 深圳市国华光电研究院 | RSSR-based LED indoor positioning method and system thereof |
CN111479231A (en) * | 2020-04-17 | 2020-07-31 | 西安交通大学 | Indoor fingerprint positioning method for millimeter wave large-scale MIMO system |
CN113099384A (en) * | 2020-11-11 | 2021-07-09 | 中移(上海)信息通信科技有限公司 | Indoor positioning method, device, equipment and computer storage medium |
CN114492715A (en) * | 2021-12-28 | 2022-05-13 | 西安电子科技大学 | Improved sparrow searching method based on chaotic reverse learning and self-adaptive spiral searching |
CN115436878A (en) * | 2022-09-28 | 2022-12-06 | 浙江浙能兰溪发电有限责任公司 | Three-dimensional visible light positioning method based on received signal intensity ratio and independent of height |
CN115499916A (en) * | 2022-11-15 | 2022-12-20 | 中国人民解放军海军工程大学 | Wireless sensor network node positioning method based on improved whale optimization algorithm |
WO2023040228A1 (en) * | 2021-09-17 | 2023-03-23 | 湖北文理学院 | Visible light positioning assisted multi-user light communication system and method |
CN116938066A (en) * | 2023-06-28 | 2023-10-24 | 郑州轻工业大学 | Permanent magnet synchronous motor parameter identification method based on dung beetle optimization algorithm |
-
2023
- 2023-11-28 CN CN202311599530.8A patent/CN117576225B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105823477A (en) * | 2016-03-09 | 2016-08-03 | 深圳市国华光电研究院 | RSSR-based LED indoor positioning method and system thereof |
CN111479231A (en) * | 2020-04-17 | 2020-07-31 | 西安交通大学 | Indoor fingerprint positioning method for millimeter wave large-scale MIMO system |
CN113099384A (en) * | 2020-11-11 | 2021-07-09 | 中移(上海)信息通信科技有限公司 | Indoor positioning method, device, equipment and computer storage medium |
WO2022099999A1 (en) * | 2020-11-11 | 2022-05-19 | 中移(上海)信息通信科技有限公司 | Indoor positioning method, apparatus and device, and storage medium |
WO2023040228A1 (en) * | 2021-09-17 | 2023-03-23 | 湖北文理学院 | Visible light positioning assisted multi-user light communication system and method |
CN114492715A (en) * | 2021-12-28 | 2022-05-13 | 西安电子科技大学 | Improved sparrow searching method based on chaotic reverse learning and self-adaptive spiral searching |
CN115436878A (en) * | 2022-09-28 | 2022-12-06 | 浙江浙能兰溪发电有限责任公司 | Three-dimensional visible light positioning method based on received signal intensity ratio and independent of height |
CN115499916A (en) * | 2022-11-15 | 2022-12-20 | 中国人民解放军海军工程大学 | Wireless sensor network node positioning method based on improved whale optimization algorithm |
CN116938066A (en) * | 2023-06-28 | 2023-10-24 | 郑州轻工业大学 | Permanent magnet synchronous motor parameter identification method based on dung beetle optimization algorithm |
Non-Patent Citations (5)
Title |
---|
High-Accuracy Height-Independent 3D VLP Based on Received Signal Strength Ratio;Yihuai Xu et al;Sensors;20220921;第22卷(第19期);摘要,第1-3部分 * |
基于白光LED的室内高精度定位算法的实现;高燕龙;施安存;张运方;李慧;盖轶冰;段靖远;刘育梁;;半导体光电;20150215(第01期);全文 * |
室内可见光定位的几种技术对比;陈至琪;;科学技术创新;20200105(第01期);全文 * |
稀疏训练指纹库融合MMPSO-ELM室内可见光定位;张慧颖 等;激光技术;20221130;第46卷(第6期);摘要,引言和第二部分 * |
采用投影螺旋搜索的改进粒子群算法;高嘉乐;邢清华;李龙跃;范成礼;;西安交通大学学报;20180327(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117576225A (en) | 2024-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108732537B (en) | Indoor visible light positioning method based on neural network and received signal intensity | |
CN103308463B (en) | Characteristic spectrum area selection method for near infrared spectrum | |
CN110942205B (en) | Short-term photovoltaic power generation power prediction method based on HIMVO-SVM | |
CN108802674A (en) | It is a kind of for the combined method for searching and device that directly position | |
CN111818449A (en) | Visible light indoor positioning method based on improved artificial neural network | |
CN110412534A (en) | Based on the stealthy radar network multiple target tracking residence time optimization method of radio frequency | |
CN105719101A (en) | Photovoltaic system power generation power prediction method | |
CN117576225B (en) | Indoor visible light positioning method and system based on received signal strength ratio | |
CN110264006B (en) | Wind power probabilistic prediction method based on chaotic firefly algorithm and Bayesian network | |
CN111562548A (en) | Indoor visible light joint positioning method based on RSS and position fingerprints | |
CN113219408A (en) | Improved RBF neural network indoor visible light positioning method and system | |
CN108365891B (en) | Method for optimizing downlink coverage uniformity of indoor visible light communication system | |
CN117440554B (en) | Scene modeling method and system for realizing LED light source based on digitization | |
Amanor et al. | Link performance improvement via design variables optimization in LED-based VLC system for inter-satellite communication | |
CN112347597A (en) | Method for improving LED illumination uniformity based on improved particle swarm optimization | |
CN117062008A (en) | UWB positioning method based on chaotic gold sinusoidal flying dung beetle optimization algorithm | |
CN116800364A (en) | LUNA lunar base communication channel method based on ray tracing method | |
Chaabna et al. | Study of RSS-based indoor positioning system for target using visible light communication | |
Shu et al. | An interference recognition method based on improved genetic algorithm | |
Nath et al. | Weighted sum based outdoor sports lighting designing using meta-heuristic algorithms | |
Chandirasekaran et al. | A case study of bio-optimization techniques for wireless sensor network in node location awareness | |
CN104539360A (en) | Method and device for optimizing visible light communication receipt signal power | |
US11288856B2 (en) | Method and system for wave propagation prediction | |
CN115314092A (en) | Pearson coefficient-based multi-array visible light OGSM-MIMO antenna selection method | |
Sánchez-Rodríguez et al. | Performance analysis of classification methods for indoor localization in VLC networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |